Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:227708832b49ac7061c8c8cedfec3f38b21c76d72436fca62de0d18c0032ab53
+oid sha256:54920ba191c3897d93abfae0a14a21bd7a86a9692f46148ebd173663fb27535f
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d9fb08196de88b0882b7cc0b21ec7bbcdafdbe26d855d24029b88bdd529d41c
+oid sha256:9701a6fcd0bec7a7a691c63dc3f672f22d9831364b8c114a2763218f599fac02
 size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4430b9a08c075060ef6b7ad7a7977beb00c91a14854ffdc791c60cb3093cb1e9
+oid sha256:94ab18e1d59252106afdf4da18e343f22032a2767a4c2723009e6558803b0e96
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c5a8c7855b3cc55dff44b95db370c984be8d56bad23c2aea8770dee5814ed88
+oid sha256:f915568f86cbbb4ec27d1f37808bebd339a27f0f49c65b6033fc00a9a70a87ef
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.5615507960319519,
-  "best_model_checkpoint": "miner_id_24/checkpoint-300",
-  "epoch": 0.11374407582938388,
+  "best_metric": 0.53005450963974,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.17061611374407584,
   "eval_steps": 150,
-  "global_step": 300,
+  "global_step": 450,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -241,6 +241,119 @@
       "eval_samples_per_second": 21.057,
       "eval_steps_per_second": 5.267,
       "step": 300
+    },
+    {
+      "epoch": 0.11753554502369669,
+      "grad_norm": 0.8847883343696594,
+      "learning_rate": 9.753026828739756e-05,
+      "loss": 0.9371,
+      "step": 310
+    },
+    {
+      "epoch": 0.12132701421800948,
+      "grad_norm": 0.840414822101593,
+      "learning_rate": 9.733837129832993e-05,
+      "loss": 0.5609,
+      "step": 320
+    },
+    {
+      "epoch": 0.12511848341232226,
+      "grad_norm": 0.8552011251449585,
+      "learning_rate": 9.713949874763296e-05,
+      "loss": 0.4904,
+      "step": 330
+    },
+    {
+      "epoch": 0.12890995260663507,
+      "grad_norm": 0.7504507899284363,
+      "learning_rate": 9.693367994023828e-05,
+      "loss": 0.4276,
+      "step": 340
+    },
+    {
+      "epoch": 0.13270142180094788,
+      "grad_norm": 0.7728025317192078,
+      "learning_rate": 9.672094520464552e-05,
+      "loss": 0.3153,
+      "step": 350
+    },
+    {
+      "epoch": 0.13649289099526066,
+      "grad_norm": 0.8927388191223145,
+      "learning_rate": 9.650132588845318e-05,
+      "loss": 0.8539,
+      "step": 360
+    },
+    {
+      "epoch": 0.14028436018957346,
+      "grad_norm": 0.9280526638031006,
+      "learning_rate": 9.627485435373948e-05,
+      "loss": 0.5319,
+      "step": 370
+    },
+    {
+      "epoch": 0.14407582938388624,
+      "grad_norm": 0.8443691730499268,
+      "learning_rate": 9.604156397229367e-05,
+      "loss": 0.4799,
+      "step": 380
+    },
+    {
+      "epoch": 0.14786729857819905,
+      "grad_norm": 0.8244546055793762,
+      "learning_rate": 9.580148912069836e-05,
+      "loss": 0.4255,
+      "step": 390
+    },
+    {
+      "epoch": 0.15165876777251186,
+      "grad_norm": 0.587851881980896,
+      "learning_rate": 9.555466517526405e-05,
+      "loss": 0.3149,
+      "step": 400
+    },
+    {
+      "epoch": 0.15545023696682464,
+      "grad_norm": 0.9294399619102478,
+      "learning_rate": 9.53011285068163e-05,
+      "loss": 0.8398,
+      "step": 410
+    },
+    {
+      "epoch": 0.15924170616113745,
+      "grad_norm": 0.8756105303764343,
+      "learning_rate": 9.50409164753362e-05,
+      "loss": 0.5178,
+      "step": 420
+    },
+    {
+      "epoch": 0.16303317535545023,
+      "grad_norm": 0.7490562796592712,
+      "learning_rate": 9.477406742445516e-05,
+      "loss": 0.4677,
+      "step": 430
+    },
+    {
+      "epoch": 0.16682464454976303,
+      "grad_norm": 0.8731195330619812,
+      "learning_rate": 9.450062067580488e-05,
+      "loss": 0.4073,
+      "step": 440
+    },
+    {
+      "epoch": 0.17061611374407584,
+      "grad_norm": 0.7838053107261658,
+      "learning_rate": 9.422061652322298e-05,
+      "loss": 0.2986,
+      "step": 450
+    },
+    {
+      "epoch": 0.17061611374407584,
+      "eval_loss": 0.53005450963974,
+      "eval_runtime": 211.0482,
+      "eval_samples_per_second": 21.047,
+      "eval_steps_per_second": 5.264,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -269,7 +382,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.6549838985927066e+17,
+  "total_flos": 3.9862471318359245e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null